• Leading a data science team to design and execute data science roadmaps, with a focus on developing, optimising modelling pipelines, and driving automation initiatives.• Led the development and implementation of advanced machine learning algorithms to scale Premium’s NEO segmentation across a 21M-strong Australian audience which enabled targeted marketing across addressable channels.• Productionised look-alike models to predict audience with similar demographics, lifestyle, interest and consumer behaviour leveraging multiple datasets.• Cross-functional collaboration with data architects, data engineers and BI engineers to automate, optimise and visualise various ML pipelines, enhancing efficiency and profitability through reduced manual intervention.• Coordinated with multiple data partners to facilitate successful bi-annual data updates, ensuring data integrity, accuracy and scalability.• Led efforts to transform and migrate various ML pipelines from R to Python.

• Leveraged video on demand viewership data to apply K-Nearest Neighbour (KNN) modelling against the matched universe, identifying users within the unmatched universe who have similar consumption behaviours. This resulted in expanding HVA reach in publisher channels to 80%.• Acquired, cleansed, transformed, and verified data from first, second, and third-party data sources.• Interpreted data, analysed results, and identified trends using statistical techniques and provide ongoing insights/measurement reports.• Created data modelling pipelines and workflows to perform customer segmentation through look-alike modelling and k-means clustering. • Managed end to end client delivery which involves internal stakeholders, data collection & preparation, quality control and delivering accurate/timely models & insights.• Liaised with key internal SBUs / agencies to verify data integrity, model accuracy, and seeked input for client presentations.• Proactively engaged leaders across the business to build a data science profile and identified new business opportunities.• Carried out data auditing and provided analysis for new business pitches as directed.

• Prioritisation of field of opportunities for urban cooling in Melbourne. • Analysing vegetation data using QGIS and python and prioritising shading and irrigation opportunities in open space to benefit the population. • Also, analysing and improving accessibility of the population to these open spaces.

• Proposed a proof of concept to visually represent the operation of drainage network which is based on the latest technologies and operating environment. The concept was also based on the future workforce in 10 years and how these technologies and visualization would impact their work.• Carried out research to find out which technologies or integration of multiple technologies would help the Melbourne Water to effectively visualize the drainage network in future and efficiently check the performance of their assets as well.